Tag: #rag
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 58 posts
Document AI / OCR in 2026 — Mistral OCR / Marker / Surya / LlamaParse / Docling / OlmoOCR Deep Dive
Document AI in 2026 is no longer "extract text with Tesseract." Purpose-built APIs like Mistral OCR (March 2025), open-source PDF-to-Markdown engines like Marker / Surya / Docling / OlmoOCR, pretrained document models li
2026-05-15 · 19 min read #ocr#document-ai#pdf#mistral-ocr#markerThe 2026 Vector DB Landscape — Pinecone Serverless, Turbopuffer, pgvectorscale, Qdrant, Weaviate, Vespa, and What Actually Changed
The vector-DB comparison post you wrote in 2024 is already stale. Pinecone Serverless collapsed pricing, Turbopuffer put 2.5 trillion vectors on S3, pgvectorscale added StreamingDiskANN, Qdrant ripped out RocksDB, Weavia
2026-05-14 · 17 min read #vector-database#pinecone#turbopuffer#pgvector#qdrantAI Engineering in Practice — LLM API, RAG, Agents, LoRA/DPO, Vector DB, Evaluation, Observability, Prompt Injection (2025)
The real difficulty of production LLM API calls, why RAG is not simple lookup, agent patterns (ReAct, Plan-Execute, ReWOO), when to and when NOT to fine-tune (LoRA, QLoRA, DPO), a vector DB decision matrix, why LLM evalu
2026-04-15 · 7 min read #ai-engineering#llm#rag#ai-agent#loraElasticsearch, OpenSearch, and Lucene Internals — Inverted Index, BM25, Sharding, Vector Search, Hybrid RAG (2025)
Why is search hard? Lucene Segments and Merge, the math of Inverted Index, how BM25 beat TF-IDF, primary/replica shards and routing, Ingest pipelines, the Query DSL maze, kNN and HNSW, the 2021 Elastic vs AWS license war
2026-04-15 · 11 min read #elasticsearch#opensearch#lucene#search#vector-searchANN Algorithms Complete Guide 2025: HNSW, IVF, Product Quantization, LSH — How Vector DBs Really Work
How Pinecone, Weaviate, Qdrant, and pgvector find similar items in milliseconds across hundreds of millions of vectors. A deep dive into the math and implementation of HNSW, IVF, Product Quantization, and LSH.
2026-04-15 · 14 min read #ann#hnsw#ivf#product-quantization#lshAdvanced RAG Pipeline Complete Guide 2025: Chunking Strategies, Re-ranking, Agentic RAG, Evaluation
Everything about Advanced RAG! Document chunking strategies (Semantic/Recursive/Agentic), re-ranking (Cohere/ColBERT/Cross-encoder), Query Transformation, Agentic RAG (Self-RAG/CRAG), Multi-modal RAG, Evaluation (RAGAS/T
2026-04-13 · 23 min read #rag#chunking#reranking#agentic-rag#evaluationMastra Practical Guide: Why TypeScript Teams Adopt It for Production AI Agents in 2026
A practical guide to Mastra for TypeScript teams that need agents, memory, workflows, observability, evals, and production deployment in one open-source stack.
2026-04-12 · 6 min read #mastra#typescript#ai-agent#mcp#memoryLlamaIndex Workflows Practical Guide: How to Ship Event-Driven Agents and RAG to Production
A practical guide to LlamaIndex Workflows for event-driven agent and RAG design, with observability, human-in-the-loop patterns, and production rollout guidance through LlamaDeploy.
2026-04-12 · 5 min read #llamaindex#workflows#agent-workflow#rag#observabilityOpenAI AI Deployment Engineer (Seoul) Complete Guide: Roadmap to Deploying GPT for the Enterprise
A complete analysis of the OpenAI Seoul AI Deployment Engineer JD. Deploying GPT to Fortune 500 companies — deep dive into Python, K8s, RAG, LangGraph, agentic workflows, model fine-tuning + 3-stage interview strategy +
2026-03-23 · 25 min read #openai#ai-deployment-engineer#python#kubernetes#ragVector Database Engineer Career Guide: Pinecone vs Weaviate vs Milvus Complete Comparison for the RAG Era
Complete analysis of Vector Database, the core infrastructure of the RAG era. Architecture, performance, and pricing comparison of 6 major vector DBs: Pinecone, Weaviate, Milvus, Qdrant, pgvector, and Chroma. Embedding m
2026-03-23 · 30 min read #vector-database#pinecone#weaviate#milvus#qdrantDatabricks AI Engineer (FDE) Complete Guide: Spark, Unity Catalog, RAG to Customer Deployment
A complete analysis of the Databricks AI Engineer (FDE) JD. From Spark/Delta Lake/Unity Catalog tech stack, Lakehouse architecture, RAG pipeline construction, to customer deployment skills — 25 interview questions and an
2026-03-23 · 34 min read #databricks#fde#spark#delta-lake#unity-catalogVector Database Comparison 2025: Pinecone vs Weaviate vs Chroma vs pgvector
A practical 2025 comparison of Pinecone, Weaviate, Chroma, and pgvector across performance, cost, and operational complexity. Includes real code examples and a decision matrix to help you pick the right vector database f
2026-03-18 · 8 min read #vector-database#pinecone#weaviate#chroma#pgvectorRAG vs Fine-tuning vs Prompt Engineering: The Complete Decision Framework
A practical comparison of RAG, fine-tuning, and prompt engineering from a production engineering perspective, with a concrete decision framework, real cost calculations, and honest gotchas from building these systems in
2026-03-18 · 7 min read #rag#fine-tuning#prompt-engineering#llm#ai-developmentEmbedding Model Selection Guide 2025: From OpenAI to Open-Source Options
A practical 2025 comparison of the major embedding models — OpenAI, Cohere, BGE-M3, E5-mistral, nomic-embed — with MTEB benchmark analysis, language-specific recommendations, and a decision framework for choosing the rig
2026-03-18 · 9 min read #embedding#embedding-model#rag#ai-development#openaiRAG Chunking Strategies: From Naive Splitting to RAPTOR
Chunking determines 70% of your RAG system quality. This guide covers 5 chunking strategies with real code — from simple fixed-size splitting to Semantic Chunking, Parent-Child, and RAPTOR — with honest assessments of wh
2026-03-18 · 8 min read #rag#chunking#text-splitting#langchain#raptorHybrid Search Guide: Combining BM25 and Vector Search for Better RAG
Pure vector search has a blind spot: exact keyword matching. This guide explains how to combine BM25 and vector search using RRF (Reciprocal Rank Fusion) to get the best of both worlds — with real code, benchmark numbers
2026-03-18 · 7 min read #hybrid-search#bm25#vector-search#rag#rrfLLM Hallucination: Why AI Makes Things Up and 5 Strategies to Prevent It
A technical deep-dive into why LLMs hallucinate, covering all four hallucination types and five practical prevention strategies including RAG, self-critique pipelines, Chain of Verification, and temperature tuning — all
2026-03-18 · 9 min read #hallucination#llm#ai-reliability#ai-development#rag1 Million Token Context Windows: Is RAG Becoming Obsolete?
With Gemini 1.5 Pro's 1M token context and Claude's 200K, many developers ask: why bother with RAG? We compare real costs, latency, and quality to give you an honest answer.
2026-03-18 · 6 min read #context-window#rag#llm#long-context#ai-developmentGraphRAG Complete Guide: How Knowledge Graphs Overcome RAG Limitations
Standard RAG fails on global queries like "summarize the key risk themes across all these documents." We walk through how Microsoft Research's GraphRAG solves this, with real code and honest cost analysis.
2026-03-18 · 8 min read #graphrag#knowledge-graph#rag#microsoft#ai-developmentRAG Systems Complete Guide: Everything About Retrieval-Augmented Generation
A complete guide to mastering RAG (Retrieval-Augmented Generation) systems. From basic RAG to advanced Self-RAG, Corrective-RAG, and HyDE — covering vector databases, embedding models, chunking strategies, and reranking
2026-03-17 · 23 min read #rag#llm#vector-database#langchain#embedding